|Table of Contents|

[1] Zhang Suofei, Filliat David, Wu Zhenyang,. Online object detection and recognitionusing motion information and local feature co-occurrence [J]. Journal of Southeast University (English Edition), 2012, 28 (4): 404-409. [doi:10.3969/j.issn.1003-7985.2012.04.006]
Copy

Online object detection and recognitionusing motion information and local feature co-occurrence()
基于运动信息和局部特征并发性的在线目标检测和识别
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
28
Issue:
2012 4
Page:
404-409
Research Field:
Computer Science and Engineering
Publishing date:
2012-12-30

Info

Title:
Online object detection and recognitionusing motion information and local feature co-occurrence
基于运动信息和局部特征并发性的在线目标检测和识别
Author(s):
Zhang Suofei1;  Filliat David2;  Wu Zhenyang1
1Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education, Southeast University, Nanjing 210096, China
2UEI, ENSTA ParisTech, Paris 91762, France
张索非1;  Filliat David2;  吴镇扬1
1东南大学水声信号处理教育部重点实验室, 南京 210096; 2UEI, ENSTA ParisTech, Paris 91762, France
Keywords:
object recognition;  online learning;  motion information;  computer vision
目标识别;  在线学习;  动作信息;  机器视觉
PACS:
TP391.4
DOI:
10.3969/j.issn.1003-7985.2012.04.006
Abstract:
An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.
实现了一个为类人型机器人设计的目标学习和识别系统, 机器人可以利用该系统仅通过和非专业用户简单的互动来发现并记住目标.当目标展示时, 系统利用连续帧间的运动信息提取目标特征并基于视觉单词包方法实现机器学习.在目标模型的学习与测试阶段, 不仅直接使用了局部特征描述子, 还使用了局部特征的并发性以提升特征的可鉴别性.同时, 针对目标视觉特征的纹理程度, 还采用了一种混合的采样策略.该混合策略使用了更小的计算资源开销并在一个12类常见目标构成的集合上取得了良好的识别效果.

References:

[1] Sivic J, Zisserman A. Video Google: a text retrieval approach to object matching in videos [C]//IEEE International Conference on Computer Vision. Nice, France, 2003: 1470-1477.
[2] Lowe D. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[3] Bay H, Tuytelaars T, Van Gool L. Surf: speeded up robust features [C]//European Conference on Computer Vision. Graz, Austria, 2006: 404-417.
[4] Micusik B, Kosecka J. Semantic segmentation of street scenes by superpixel co-occurrence and 3d geometry [C]//IEEE 12th International Conference on Computer Vision Workshops. Kyoto, Japan, 2009: 625-632.
[5] Nowak E, Jurie F, Triggs B. Sampling strategies for bag-of-features image classification [C]//European Conference on Computer Vision. Graz, Austria, 2005: 490-503.
[6] Filliat D. Interactive learning of visual topological navigation [C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice, France, 2008:248-254.
[7] Filliat D. A visual bag of words method for interactive qualitative localization and mapping [C]//IEEE International Conference on Robotics and Automation. Roma, Italy, 2007: 3921-3926.
[8] Jurie F, Triggs B. Creating efficient codebooks for visual recognition [C]//IEEE International Conference on Computer Vision. Beijing, China, 2005: 604-610.
[9] Nister D, Stewenius H. Scalable recognition with a vocabulary tree [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006: 2161-2168.
[10] Parikh D, Zitnick C, Chen T. Determining patch saliency using low-level context [C]//European Conference on Computer Vision. Marseille, France, 2008: 446-459.
[11] Torralba A, Murphy K, Freeman W. Sharing visual features for multiclass and multiview object detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(5): 854-869.
[12] Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting [J]. The Annals of Statistics, 2000, 28(2): 337-374.

Memo

Memo:
Biographies: Zhang Suofei(1982—), male, graduate; Wu Zhenyang(corresponding author), male, doctor, professor, zhenyang@seu.edu.cn.
Foundation item: The National Natural Science Foundation of China(No.60672094, 60971098).
Citation: Zhang Suofei, Filliat David, Wu Zhenyang. Online object detection and recognition using motion information and local feature co-occurrence[J].Journal of Southeast University(English Edition), 2012, 28(4):404-409.[doi:10.3969/j.issn.1003-7985.2012.04.006]
Last Update: 2012-12-20